© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89517
    Prev
    Next
    INDEX
    Explanations

    who questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wouldn
    -0.10
     Independence
    -0.09
     Emer
    -0.09
     Prest
    -0.09
     Schro
    -0.09
    alem
    -0.09
    fade
    -0.09
    zik
    -0.08
    bah
    -0.08
    bor
    -0.08
    POSITIVE LOGITS
     fucking
    0.12
     authorised
    0.10
     tamp
    0.10
     Stub
    0.09
     authorize
    0.09
    ring
    0.09
    AAAA
    0.09
     Authorized
    0.09
    agua
    0.09
    oser
    0.09
    Activations Density 0.013%

    No Known Activations